ORCID Profile
0000-0002-6675-3393
Current Organisation
University of Adelaide
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Oxford University Press (OUP)
Date: 11-2022
DOI: 10.1093/PNASNEXUS/PGAC258
Abstract: Hip osteoarthritis (HOA) is a degenerative joint disease that leads to the progressive destruction of subchondral bone and cartilage at the hip joint. Development of effective treatments for HOA remains an open problem, primarily due to the lack of knowledge of its pathogenesis and a typically late-stage diagnosis. We describe a novel network analysis methodology for microcomputed tomography (micro-CT) images of human trabecular bone. We explored differences between the trabecular bone microstructure of femoral heads with and without HOA. Large-scale automated extraction of the network formed by trabecular bone revealed significant network properties not previously reported for bone. Profound differences were discovered, particularly in the proximal third of the femoral head, where HOA networks demonstrated elevated numbers of edges, vertices, and graph components. When further differentiating healthy joint and HOA networks, the latter showed fewer small-world network properties, due to decreased clustering coefficient and increased characteristic path length. Furthermore, we found that HOA networks had reduced length of edges, indicating the formation of compressed trabecular structures. In order to assess our network approach, we developed a deep learning model for classifying HOA and control cases, and we fed it with two separate inputs: (i) micro-CT images of the trabecular bone, and (ii) the network extracted from them. The model with plain micro-CT images achieves 74.6% overall accuracy while the trained model with extracted networks attains 96.5% accuracy. We anticipate our findings to be a starting point for a novel description of bone microstructure in HOA, by considering the phenomenon from a graph theory viewpoint.
Publisher: Cold Spring Harbor Laboratory
Date: 25-10-2022
DOI: 10.1101/2022.10.23.22281428
Abstract: Robust and accurate prediction of cardiovascular disease (CVD) risk facilitates early intervention to benefit patients. It is well-known that mental disorders and CVD are interrelated. Nevertheless, psychological factors are not considered in existing models, which use either a limited number of clinical and lifestyle factors, or have been developed on restricted population subsets. To assess whether inclusion of psychological data could improve CVD risk prediction in a new machine learning (ML) approach. Using a comprehensive, long-term UK Biobank dataset (n=375,145), we examined the correlation between CVD diagnoses and traditional and psychological risk factors. An ensemble ML model containing five constituent algorithms [decision tree, random forest, XGBoost, support vector machine (SVM), and deep neural network (DNN)] was tested for its ability to predict CVD risk based on two training datasets: one using traditional CVD risk factors alone, or a combination of traditional and psychological risk factors. Our ensemble ML model could predict CVD with 71.31% accuracy using traditional CVD risk factors alone. However, by adding psychological factors to the training data, accuracy dramatically increased to 85.13%. The accuracy and robustness of our ensemble ML model outperformed all five constituent learning algorithms. Re-testing the model on a control dataset to predict bone diseases returned random results, confirming specificity of the training data for prediction of CVD. Incorporating mental health assessment data within an ensemble ML model results in a significantly improved, highly accurate, state-of-the-art CVD risk prediction. All authors have seen and approved the manuscript. The authors declare no competing interests. All data needed to evaluate the conclusions in the paper are present in the paper or in the supplementary materials. In addition, we used UK Biobank in this study: www.ukbiobank.ac.uk . No funding.
Publisher: Springer Science and Business Media LLC
Date: 17-03-2020
DOI: 10.1038/S41598-020-62013-Y
Abstract: An amendment to this paper has been published and can be accessed via a link at the top of the paper.
Publisher: The Royal Society
Date: 03-2019
DOI: 10.1098/RSOS.182001
Abstract: The instantaneous frequency (IF) of a signal is a well-defined quantity that is widely used for analysing non-stationary signals. However, often in practice, IF as a function of time can possess large spikes and negative values. Moreover, IF is very sensitive to noise, limiting its range of practical application. Due to these deficiencies, we introduce the concept of moment of velocity (MoV) for signal analysis. As a case study, we compare the performance of MoV to a standard Hilbert transform-based approach for R-wave identification in human electrocardiogram signals, demonstrating that our approach is more robust to noise. We examine characteristic heartbeats obtained from the MIT-BIH Arrhythmia database. A detection error rate of 0.07%, a positive predictive value of 99.97%, and a sensitivity of 99.95% are achieved against analysis results from the database.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: The Royal Society
Date: 11-2019
DOI: 10.1098/RSOS.190671
Abstract: Many physical systems can be adequately modelled using a second-order approximation. Thus, the problem of system identification often reduces to the problem of estimating the position of a single pair of complex–conjugate poles. This paper presents a convenient but approximate technique for the estimation of the position of a single pair of complex–conjugate poles, using the moment of velocity (MoV). The MoV is a Hilbert transform based signal processing tool that addresses the shortcomings of instantaneous frequency. We demonstrate that the MoV can be employed for parameter identification of a dynamical system. We estimate the d ing coefficient and oscillation frequency via MoV of the impulse response.
Publisher: Springer Science and Business Media LLC
Date: 20-06-2019
DOI: 10.1038/S41598-019-45253-5
Abstract: The truel is a three person competition that generalises the classic duel. In this game three players try to eliminate each other in a series of one-to-one duels until there is only one survivor. The players’ marksmanship, shooting order and strategies for choosing a target play a significant role in in idual’s survival probability. Strategies such as shooting into the air (abstention), shooting at the strongest opponent, and shooting at the weakest opponent have been analysed in the previous literature. In this paper, for the first time, we consider suicidal and random strategies that can be chosen by the weaker player. We show that although there is no possible highest probability region for weakest player adopting suicidal strategy, the player may increase the survival probability via switching between suicidal and abstention strategies randomly. In addition, we demonstrate that there is a narrow survival area for the weakest player when the player aims randomly at two other opponents, and eventually the area fades away if the player fires randomly at himself or the other two opponents.
Publisher: Springer Science and Business Media LLC
Date: 22-09-2021
DOI: 10.1038/S42003-021-02632-X
Abstract: The growth of solid tumours relies on an ever-increasing supply of oxygen and nutrients that are delivered via vascular networks. Tumour vasculature includes endothelial cell lined angiogenesis and the less common cancer cell lined vasculogenic mimicry (VM). To study and compare the development of vascular networks formed during angiogenesis and VM (represented here by breast cancer and pancreatic cancer cell lines) a number of in vitro assays were utilised. From live cell imaging, we performed a large-scale automated extraction of network parameters and identified properties not previously reported. We show that for both angiogenesis and VM, the characteristic network path length reduces over time however, only endothelial cells increase network clustering coefficients thus maintaining small-world network properties as they develop. When compared to angiogenesis, the VM network efficiency is improved by decreasing the number of edges and vertices, and also by increasing edge length. Furthermore, our results demonstrate that angiogenic and VM networks appear to display similar properties to road traffic networks and are also subject to the well-known Braess paradox. This quantitative measurement framework opens up new avenues to potentially evaluate the impact of anti-cancer drugs and anti-vascular therapies.
Publisher: Cold Spring Harbor Laboratory
Date: 29-03-2022
DOI: 10.1101/2022.03.28.486155
Abstract: Hip osteoarthritis (HOA) is a degenerative joint disease that leads to the progressive destruction of subchondral bone and cartilage at the hip joint. Development of effective treatments for HOA remains an open problem, primarily due to the lack of knowledge of its pathogenesis and a typically late-stage diagnosis. We describe a novel network analysis methodology for micro-computed tomography (micro-CT) images of human trabecular bone. We explored differences between the trabecular bone microstructure of femoral heads with and without HOA. Large-scale automated extraction of the network formed by trabecular bone revealed significant network properties not previously reported for bone. Profound differences were discovered, particularly in the proximal third of the femoral head, where HOA networks demonstrated elevated numbers of edges, vertices and graph components. When further differentiating healthy joint and HOA networks, the latter showed fewer small-world network properties, due to decreased clustering coefficient and increased characteristic path length. Furthermore, we found that HOA networks had reduced length of edges, indicating the formation of compressed trabecular structures. In order to assess our network approach, we developed a deep learning model for classifying HOA and control cases, and we fed it with two separate inputs: ( i ) micro-CT images of the trabecular bone, and ( ii ) the network extracted from them. The model with plain micro-CT images achieves 74.63% overall accuracy while the trained model with extracted networks attains 96.47% accuracy. We anticipate our findings to be a starting point for a novel description of bone microstructure in HOA, by considering the phenomenon from a graph theory viewpoint.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Springer Science and Business Media LLC
Date: 10-08-2018
DOI: 10.1038/S41598-018-30469-8
Abstract: C-reactive protein (CRP) is an acute-phase plasma protein that can be used as a biomarker for activation of the immune system. A spectral analysis of CRP level over time for patients with gynaecological tumours has been reported by Madondo et al ., using a periodogram method, suggesting that there is no significant periodicity in the data. In our study, we investigate the impact of low s le number on periodogram analysis, for non-uniform s ling intervals—we conclude that data of Madondo et al . cannot rule out periodic behaviour. The search for patterns (periodic or otherwise) in the CRP time-series is of interest for providing a cue for the optimal times at which cancer therapies are best administered. In this paper we show (i) there is no evidence to rule out periodicity in CRP levels, and (ii) we provide a prescription for the minimum data s le rate required in future experiments for improved testing of a periodic CRP signal hypothesis. The analysis we provide may be used for establishing periodicity in any short time-series signal that is observed without a priori information.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
No related grants have been discovered for Mohsen Dorraki.